Department of Animal Sciences, North Dakota State University, Fargo, ND 58102, USA.
Department of Animal Science, University of Arkansas, Fayetteville, AR 72701, USA; College of Agriculture, Engineering & Technology, Arkansas State University, Jonesboro, AR 72467, USA.
Meat Sci. 2018 Sep;143:18-23. doi: 10.1016/j.meatsci.2018.03.020. Epub 2018 Mar 26.
The objective of this study was to investigate the ability of computer vision system to predict pork intramuscular fat percentage (IMF%). Center-cut loin samples (n = 85) were trimmed of subcutaneous fat and connective tissue. Images were acquired and pixels were segregated to estimate image IMF% and 18 image color features for each image. Subjective IMF% was determined by a trained grader. Ether extract IMF% was calculated using ether extract method. Image color features and image IMF% were used as predictors for stepwise regression and support vector machine models. Results showed that subjective IMF% had a correlation of 0.81 with ether extract IMF% while the image IMF% had a 0.66 correlation with ether extract IMF%. Accuracy rates for regression models were 0.63 for stepwise and 0.75 for support vector machine. Although subjective IMF% has shown to have better prediction, results from computer vision system demonstrates the potential of being used as a tool in predicting pork IMF% in the future.
本研究旨在探讨计算机视觉系统预测猪肉肌内脂肪百分比（IMF%）的能力。中心切割腰肉样品（n=85）去除皮下脂肪和结缔组织。采集图像并分割像素，以估算图像 IMF%和每个图像的 18 个图像颜色特征。主观 IMF%由经过培训的分级员确定。乙醚萃取 IMF%采用乙醚萃取法计算。图像颜色特征和图像 IMF%用作逐步回归和支持向量机模型的预测因子。结果表明，主观 IMF%与乙醚萃取 IMF%的相关性为 0.81，而图像 IMF%与乙醚萃取 IMF%的相关性为 0.66。回归模型的准确率分别为逐步法的 0.63 和支持向量机的 0.75。虽然主观 IMF%显示出更好的预测能力，但计算机视觉系统的结果表明，它有可能在未来作为预测猪肉 IMF%的工具。
